D Anil Kumar

Scopus Publications

Classification of cardiac MRI images by multi resolution residual feature forged convolutional vision transformer (MrRf2 -CViT)
P V V Kishore, D Anil Kumar
Engineering Research Express, 2026
Vision Transformers (ViT) have displayed unprecedented success in the segmentation of Left Ventricle (LV), right ventricle (RV) and myocardial (MYO) functions from cardiac MRI (CMRI) images that helped in the classification of cardiovascular diseases (CVDs). ViT based segmentation is a computationally intensive and data extensive training operation. Classification of CMRI data without segmentation modules is challenging because of the relatively less spatial dimensionality and movement artifacts of the cardiac function. To overcome this, we investigated convolutional feature projection with ViT encoders (CViT) for CMRI CVD classification which has been influenced by scale, shift and deformations of features during the training process. To improve CViT classification of CVDs through CMRI data, we propose Multi Resolution Feature Forged Convolutional Vision Transformer (MrRf 2 —CViT). Contrasting to traditional CViT’s positional encoding and convolutional projection of patched image features, the MrRf 2 —CNN generates relational features at different scales on a pre-defined set of image sequences. These consecutively extracted image features are flattened, tokenized, and are linearly projected with ViT’s encoder for classification. This MrRf 2 -CViT model leverages the transformer’s attention and context association capabilities to accomplish shift and scale invariance in sequential CMRI data. Specifically, the MrRf 2 -CViT learns the patterns within dynamic heart movements represented spatially by convolutional features that are effectively localized with ViT’s attention mechanism for detecting the CVDs. Sunnybrook Cardiac (SCM) and Automated Cardiac Diagnosis Challenge (ACDC) MRI data has been applied to the proposed MrRf 2 -CViT for evaluation. The experiments conducted show an increase in performance of the proposed approach (MrRf 2 -CViT) over state—of—the—art MRI image classification methods.
Stretched image resolution augmented attention for classification of paediatric cough sounds using smart phone microphonic recordings
P V V Kishore, D Anil Kumar, K Dikshitha, Soans Santosh, Gnane Swarnadh Satapathi
Engineering Research Express, 2026
Cough-sound analysis offers a low-cost, rapid screening pathway for acute respiratory infections (ARIs), but deep-learning models trained on fixed-resolution Mel-spectrogram images often generalize poorly because cough events exhibit substantial within-class spatio-temporal variability across subjects and recording conditions. To address this, we propose Stretched Image Resolution Augmented Attention (SIRAA), a multi-stream convolutional framework that learns complementary representations from multi-resolution log-Mel spectrogram images generated by systematically varying two MFCC design parameters: the number of Mel filters and FFT size. SIRAA processes three resolutions in parallel and performs resolution-conditioned feature fusion via an augmented attention mechanism, injecting high-resolution local cues and low-resolution global structure into a central stream used for final classification. We introduce IndiCough2024, a clinician-labelled pediatric cough dataset collected using smartphones in a hospital setting, comprising 503 children (1–6 years) and five diagnostic classes: asthma, pneumonia, upper respiratory tract infection, lower respiratory tract infection, and croup. On IndiCough2024, SIRAA achieves up to 95.7% top-1 accuracy and yields greater than 18 percentage-point improvement over comparable single-resolution training pipelines. Additional benchmarking on public cough datasets further supports the robustness of the proposed multi-resolution augmented attention strategy for cough-based multi-class respiratory screening.
Optimizing continuous sign language recognition through motion selective sparse spatial feature extraction
V Prathyusha, P V V Kishore, D Anil Kumar, G V K Murthy
Engineering Research Express, 2025
Continuous sign language recognition (CSLR) faces challenges due to variations in motion on spatial features across consecutive frames, affecting the performance of visual feature extraction models. This paper proposes Motion Selective Sparse Spatial Features (MS3F) to represent motion-rich visual information across video frames. MS3F extracts contextual spatial features by optimizing cross-modal loss between visual and text features, computes frame differencing to construct motion feature vectors, and uses a gated recurrent unit (GRU) to learn motion-selective sparse spatial features. A bidirectional long-short term memory network (Bi-LSTM) is then trained to learn temporal dependencies in MS3F features for tokenized targeted glosses. Experiments on the novel Doordarshan Continuous Indian Sign Language (DC-ISL) dataset, along with established benchmarks RWTH-Phoenix-2014 and Chinese-CSL (CCSL), demonstrate the effectiveness of MS3F, achieving word error rates (WERs) of 20.1%, 19.8%, and 19.9%, respectively. Compared to dense baseline models, MS3F improves WER by 2.9% to 3.4% across datasets while reducing inference time by 30% to 34% and GPU memory consumption by 22% to 27%. The motion-selective sparsity mechanism achieves approximately 30% feature reduction, processing only motion-rich frames and enabling real-time performance on standard GPU hardware. This work demonstrates that MS3F effectively captures visual information containing significant motion content while maintaining computational efficiency, advancing practical CSLR technology for real-world deployment.
Est3D2Real-estimated 3D-to-real data embeddings for real time sign language recognizer
Kishore P.V.V., Anil Kumar D.
Pattern Recognition Letters, 2025
Acute Respiratory Infections Identification With Cough Sounds and Overlapping Patch Modulated Vision Transformers
P. V. V. Kishore, D. Anil Kumar, Pasupuleti Sasikiran, Kaja Krishna Mohan, P. Praveen Kumar, Mogadala Vinod Kumar
IEEE Access, 2025
Rapid detection of Acute Respiratory Infections (ARI) is crucial to reduce breathing difficulties and severe life-threatening conditions. Automatic cough identification is being conducted using speech frequency analysis and machine learning models. Learning models trained on Mel frequency spectrum(MFCC) features of cough sounds represented as images have recorded an average binary classification accuracy of 68%. Variable cough sound vs silent intervals between samples of a class in MFCC spectral images has shown to influence training algorithms to learn meaningful patterns for classification. To learn all possible local patterns in the MFCC cough images using a vision transformer model (ViT), we propose an image patch overlapping vision transformer <inline-formula> <tex-math notation="LaTeX">$IPO-ViT$ </tex-math></inline-formula>. The patch overlapping factor <inline-formula> <tex-math notation="LaTeX">$k\\ $ </tex-math></inline-formula>controls the quantity of common pixels between them. The <inline-formula> <tex-math notation="LaTeX">$IPO-ViT$ </tex-math></inline-formula> patch encoder computes all possible local pixel pattern relationships by breaking the image into overlapping patches and equating them across all classes making a balanced augmented dataset. The <inline-formula> <tex-math notation="LaTeX">$IPO-ViT$ </tex-math></inline-formula> is evaluated on our own 511 – sound cough dataset (IndiCough_2024) with 5 classes captured at AJ Institute of Medical Sciences, paediatric division along with benchmarks EPFL COUGH VID, Coswara for COVID-19 Diagnosis and Covid19-Cough. The <inline-formula> <tex-math notation="LaTeX">$IPO-ViT$ </tex-math></inline-formula> achieved higher accuracies of around 92.33% over the state-of-the-art cough sound-based disease identification networks.
Wavelet convolutional vision transformer (WCViT) for Indian classical dance identification
P. V. V. Kishore, D. Anil Kumar, G. Hima Bindu, B. Prasad, P. Praveen Kumar, R. Prasad, E. Kiran Kumar
International Journal of Information Technology Singapore, 2025
Ppent: a pose embedding refinement framework aligning estimated and motion-captured skeletons for real-time word-level sign language recognition
P. V. V. Kishore, G. Hima Bindu, B. Prasad, D. Anil Kumar, P. Praveen Kumar, M. Suneetha, P. Sasikiran, E. Kiran Kumar
International Journal of Information Technology Singapore, 2025
Deep Bharatanatyam pose recognition: a wavelet multi head progressive attention
D. Anil Kumar, P. V. V. Kishore, K. Sravani
Pattern Analysis and Applications, 2024
Sign Language Recognition (SLR): A Brisk Paired Deep Metric Attention Learning (BPDMAL) Model for Video Data Applications
P. V. V. Kishore, D. Anil Kumar, K. Srinivasa Rao
SN Computer Science, 2024
Multi frame multi-head attention learning on deep features for recognizing Indian classical dance poses
Anil Kumar D., Kishore P.V.V., Chaithanya T.R., Sravani K.
Journal of Visual Communication and Image Representation, 2024
Human action recognition from depth sensor via skeletal joint and shape trajectories with a time-series graph matching
D. Anil Kumar, E. Kiran Kumar, M. Suneetha, L. Rajasekhar
Aip Conference Proceedings, 2024
Smart water metering system
E. Kiran Kumar, D. Anil Kumar, T. Manwitha, G. Yaswanth Sai
Aip Conference Proceedings, 2024
Three stream human action recognition using Kinect
E. Kiran Kumar, D. Anil Kumar, K. Murali, P. Sasi Kiran, M. Teja Kiran Kumar
Aip Conference Proceedings, 2024
A deep learning based approach to recognize the gestures used for controlling smart wheelchair
E. Kiran Kumar, B. Pavan Kumar, L. Rajasekhar, K. Siri Chandana, D. Anil Kumar
Aip Conference Proceedings, 2024
Alternating wavelet channel and spatial attention mechanism for online video-based Indian classical dance recognition
P. V. V. Kishore, D. Anil Kumar, P. Praveen Kumar, G. Hima Bindu
International Journal of Information Technology Singapore, 2024
Machine Interpretation of Ballet Dance: Alternating Wavelet Spatial and Channel Attention Based Learning Model
P. V. V. Kishore, D. Anil Kumar, P. Praveen Kumar, D. Srihari, N. Sasikala, L. Divyasree
IEEE Access, 2024
Joint Motion Affinity Maps (JMAM) and Their Impact on Deep Learning Models for 3D Sign Language Recognition
P. V. V. Kishore, D. Anil Kumar, Rama Chaithanya Tanguturi, K. Srinivasarao, P. Praveen Kumar, D. Srihari
IEEE Access, 2024
An Efficient Proposal for Deep Learning-Based Diabetes Prediction
D Baswaraj, Ch V V Narasimha Raju, Pundru Chandra Shaker Reddy, Ajmeera Kiran, Mohammad Khaja Shaik, D Anil Kumar
2nd IEEE International Conference on Networks Multimedia and Information Technology Nmitcon 2024, 2024
Meta Triplet Learning for Multiview Sign Language Recognition
Suneetha Mopidevi, Prasad D Venkata, Vijay Polurie, D. Anil Kumar, O Koller, et al.
International Journal of Intelligent Engineering and Systems, 2023
View Invariant Human Action Recognition using Surface Maps via convolutional networks
D. Anil Kumar, P. V. V. Kishore, G.V.K. Murthy, T. R. Chaitanya, SK. Subhani
2023 IEEE International Conference on Research Methodologies in Knowledge Management Artificial Intelligence and Telecommunication Engineering Rmkmate 2023, 2023
Recognition of Indian classical dance poses in multi head attention learning framework
P. V. V. Kishore, D. Anil Kumar, SK. Khwaja Moinuddin, L. Divyasree, E. Kiran Kumar
2023 IEEE International Conference on Research Methodologies in Knowledge Management Artificial Intelligence and Telecommunication Engineering Rmkmate 2023, 2023
Pose Driven Deep Appearance Feature Learning for Action Classification
Rejeti Hima Sameer, S. Rambabu, P. V. V. Kishore, D. Anil Kumar, M. Suneetha
Lecture Notes in Networks and Systems, 2023
Pose Based Multi View Sign Language Recognition through Deep Feature Embedding
International Journal of Intelligent Engineering and Systems, 2023
3-Dimensional Indian Dance Pose Classification using Convolution-al Neural Network
D. Anil Kumar, T. Suresh Babu, E. Sai Gowtham, M. Anusha Chandana, G. V. Vineelka, K. Narendra Reddy
2023 IEEE International Conference on Research Methodologies in Knowledge Management Artificial Intelligence and Telecommunication Engineering Rmkmate 2023, 2023
Ensemble Nonlinear Machine Learning Model for Chronic Kidney Diseases Prediction
S Sampath, Mudarakola Lakshmi Prasad, Mohammad Manzoor Hussain, R Parameswari, D Anil Kumar, Pundru Chandra Shaker Reddy
2023 IEEE 3rd Mysore Sub Section International Conference Mysurucon 2023, 2023
3D sign language recognition using spatio temporal graph kernels
D. Anil Kumar, A.S.C.S. Sastry, P.V.V. Kishore, E. Kiran Kumar
Journal of King Saud University Computer and Information Sciences, 2022
Depth based Indian Classical Dance Mudra's Recognition using Support Vector Machine
D. Arpitha, M. Balasubrahmanyam, D. Anil Kumar
Proceedings 4th International Conference on Smart Systems and Inventive Technology Icssit 2022, 2022
Skeletal Action Recognition with Local Joint Perimeter Maps Learned Using Deep Metric Embedding
Tummala Chandra Suhas, Pattem Om Prakash Ravi Teja, Nakirikanti Sai Rakesh, D. Anil Kumar, P. V. V. Kishore
2022 IEEE Delhi Section Conference Delcon 2022, 2022
Early estimation model for 3D-discrete indian sign language recognition using graph matching
E. Kiran Kumar, P.V.V. Kishore, D. Anil Kumar, M. Teja Kiran Kumar
Journal of King Saud University Computer and Information Sciences, 2021
Can Skeletal Joint Positional Ordering Influence Action Recognition on Spectrally Graded CNNs: A Perspective on Achieving Joint Order Independent Learning
M. Teja Kiran Kumar, P. V. V. Kishore, B. T. P. Madhav, D. Anil Kumar, N. Sasi Kala, K. Praveen Kumar Rao, B. Prasad
IEEE Access, 2021
Multiclass support vector machine based plant leaf diseases identification from color, texture and shape features
D. Anil Kumar, P. Sudheer Chakravarthi, K. Suresh Babu
Proceedings of the 3rd International Conference on Smart Systems and Inventive Technology Icssit 2020, 2020
A four-stream ConvNet based on spatial and depth flow for human action classification using RGB-D data
D. Srihari, P. V. V. Kishore, E. Kiran Kumar, D. Anil Kumar, M. Teja Kiran Kumar, M. V. D. Prasad, Ch. Raghava Prasad
Multimedia Tools and Applications, 2020
3D sign language recognition with joint distance and angular coded color topographical descriptor on a 2 – stream CNN
E. Kiran Kumar, P.V.V. Kishore, M. Teja Kiran Kumar, D. Anil Kumar
Neurocomputing, 2020
A quad joint relational feature for 3D skeletal action recognition with circular CNNs
Proceedings IEEE International Symposium on Circuits and Systems, 2020
3D hand gesture representation and recognition through deep joint distance measurements
P. Vasavi, Suman Maloji, E. Kiran, D. Anil, N. Sasikala
International Journal of Advanced Computer Science and Applications, 2020
YogaNet: 3-D Yoga Asana Recognition Using Joint Angular Displacement Maps with ConvNets
Teja Kiran Kumar Maddala, P.V.V. Kishore, Kiran Kumar Eepuri, Anil Kumar Dande
IEEE Transactions on Multimedia, 2019
Localized region based active contours with a weakly supervised shape image for inhomogeneous video segmentation of train bogie parts in building an automated train rolling examination
N. Sasikala, P. V. V. Kishore, D. Anil Kumar, Ch. Raghava Prasad
Multimedia Tools and Applications, 2019
Multi modal spatio temporal co-trained CNNs with single modal testing on RGB–D based sign language gesture recognition
Sunitha Ravi, Maloji Suman, P.V.V. Kishore, Kiran Kumar E, Teja Kiran Kumar M, Anil Kumar D
Journal of Computer Languages, 2019
DSLR-net a depth based sign language recognition using two stream convents
International Journal of Innovative Technology and Exploring Engineering, 2019
Investigation of 3-d relational geometric features for kernel-based 3-d sign language recognition
P. Sasi Kiran, D. Anil Kumar, P.V.V. Kishore, E. Kiran Kumar, M. Teja Kiran Kumar, A.S.C.S. Sastry
Proceedings 2019 IEEE International Conference on Intelligent Systems and Green Technology Icisgt 2019, 2019
Machine learning based 2D pose estimation model for human action recognition using geometrical maps
International Journal of Innovative Technology and Exploring Engineering, 2019
Multi modal Rgb D data based Cnn training with uni modal Rgb data testing for real time sign language recognition
International Journal of Recent Technology and Engineering, 2019
Depth based 3D indian sign language recognition using adaptive kernels
International Journal of Innovative Technology and Exploring Engineering, 2019
Fusing spatio-temporal joint features for adequate skeleton based action recognition using global alignment kernel
International Journal of Engineering and Advanced Technology, 2019
S3DRGF: Spatial 3-D relational geometric features for 3-D sign language representation and recognition
D. Anil Kumar, A. S. C. S. Sastry, P. V. V. Kishore, E. Kiran Kumar, M. Teja Kiran Kumar
IEEE Signal Processing Letters, 2019
Training granular convolution neural network with depth motion maps along with joint angular displacement maps for kinect based human action recognition
Journal of Advanced Research in Dynamical and Control Systems, 2019
Indian sign language recognition using graph matching on 3D motion captured signs
D. Anil Kumar, A. S. C. S. Sastry, P. V. V. Kishore, E. Kiran Kumar
Multimedia Tools and Applications, 2018
Three-Dimensional Sign Language Recognition with Angular Velocity Maps and Connived Feature ResNet
Eepuri Kiran Kumar, P. V. V. Kishore, Maddala Teja Kiran Kumar, Dande Anil Kumar, A. S. C. S. Sastry
IEEE Signal Processing Letters, 2018
Training CNNs for 3-D Sign Language Recognition with Color Texture Coded Joint Angular Displacement Maps
E. Kiran Kumar, P. V. V. Kishore, A. S. C. S. Sastry, M. Teja Kiran Kumar, D. Anil Kumar
IEEE Signal Processing Letters, 2018
Motionlets Matching with Adaptive Kernels for 3-D Indian Sign Language Recognition
P. V. V. Kishore, D. Anil Kumar, A. S. Chandra Sekhara Sastry, E. Kiran Kumar
IEEE Sensors Journal, 2018
Indian classical dance action identification using adaboost multiclass classifier on multifeature fusion
K. V. V. Kumar, P. V. V. Kishore, D. Anil Kumar, E. Kiran Kumar
2018 Conference on Signal Processing and Communication Engineering Systems Spaces 2018, 2018
3D motion capture for Indian sign language recognition (SLR)
E. Kiran Kumar, P. V. V. Kishore, A. S. C. S. Sastry, D. Anil Kumar
Smart Innovation Systems and Technologies, 2018
Sign language conversion tool (SLCTooL) between 30 World Sign Languages
A. S. C. S. Sastry, P. V. V. Kishore, D. Anil Kumar, E. Kiran Kumar
Smart Innovation Systems and Technologies, 2018
Selfie sign language recognition with convolutional neural networks
P.V.V. Kishore, , G. Anantha Rao, E. Kiran Kumar, M. Teja Kiran Kumar, D. Anil Kumar
International Journal of Intelligent Systems and Applications, 2018
Selfie continuous sign language recognition with neural network classifier
G. Anantha Rao, P. V. V. Kishore, A. S. C. S. Sastry, D. Anil Kumar, E. Kiran Kumar
Lecture Notes in Electrical Engineering, 2018
SWIFT cognitive behavioral assessment model built on cognitive analytics of empirical mode internet of things
International Journal of Engineering and Technology Uae, 2018
Indian Classical Dance Action Identification and Classification with Convolutional Neural Networks
P. V. V. Kishore, K. V. V. Kumar, E. Kiran Kumar, A. S. C. S. Sastry, M. Teja Kiran, D. Anil Kumar, M. V. D. Prasad
Advances in Multimedia, 2018
Unifying Boundary, Region, Shape into Level Sets for Touching Object Segmentation in Train Rolling Stock High Speed Video
N. Sasikala, P.V.V. Kishore, Ch. Raghava Prasad, E. Kiran Kumar, D. Anil Kumar, M. Teja Kiran Kumar, M.V.D. Prasad
IEEE Access, 2018
Spatial Joint features for 3D human skeletal action recognition system using spatial graph kernels
International Journal of Engineering and Technology Uae, 2018
Fire detection using computer vision models in surveillance videos
Arpn Journal of Engineering and Applied Sciences, 2017
Computer vision based dance posture extraction using slic
Journal of Theoretical and Applied Information Technology, 2017
Neural network classifier for continuous sign language recognition with selfie video
G. Anantha Rao, P. V. V. Kishore, D. Anil Kumar, A. S. C. S. Sastry
Far East Journal of Electronics and Communications, 2017
Selfie continuous sign language recognition using neural network
D. Anil Kumar, P. V. V. Kishore, A. S. C. S. Sastry, P. Reddy Gurunatha Swamy
2016 IEEE Annual India Conference Indicon 2016, 2017
Indian Classical Dance Classification with Adaboost Multiclass Classifier on Multifeature Fusion
K. V. V. Kumar, P. V. V. Kishore, D. Anil Kumar
Mathematical Problems in Engineering, 2017
Continuous sign language recognition from tracking and shape features using Fuzzy Inference Engine
P.V.V. Kishore, D. Anil Kumar, Goutham E.N.D, M. Manikanta
Proceedings of the 2016 IEEE International Conference on Wireless Communications Signal Processing and Networking Wispnet 2016, 2016
Optical Flow Hand Tracking and Active Contour Hand Shape Features for Continuous Sign Language Recognition with Artificial Neural Networks
P.V.V. Kishore, M.V.D. Prasad, D. Anil Kumar, A.S.C.S. Sastry
Proceedings 6th International Advanced Computing Conference Iacc 2016, 2016
Indian sign language recognition: A comparison between ANN and FIS
Journal of Theoretical and Applied Information Technology, 2016
Indian sign language recognition system using new fusion based edge operator
Journal of Theoretical and Applied Information Technology, 2016
Edge and texture preserving hybrid algorithm for denoising infield ultrasound medical images
Journal of Theoretical and Applied Information Technology, 2016
Medical image watermarking: Run through review
Arpn Journal of Engineering and Applied Sciences, 2016
Fuzzy classifier for continuous sign language recognition from tracking and shape features
M. V. D. Prasad, P. V. V. Kishore, D. Anil Kumar, Ch. Raghava Prasad
Indian Journal of Science and Technology, 2016
Continuous sign language recognition from tracking and shape features using fis and ann
Arpn Journal of Engineering and Applied Sciences, 2016
Twofold processing for denoising ultrasound medical images
P. V. V. Kishore, K. V. V. Kumar, D. Anil kumar, M. V. D. Prasad, E. N. D. Goutham, R. Rahul, C. B. S. Vamsi Krishna, Y. Sandeep
Springerplus, 2015

D Anil Kumar

EDUCATION

RESEARCH INTERESTS

Scopus Publications

RECENT SCHOLAR PUBLICATIONS

MOST CITED SCHOLAR PUBLICATIONS